Conectar
To predict the risk of hospital-acquired pressure injury using machine learning compared with standard care.
We obtained electronic health records (EHRs) to structure a multilevel cohort of hospitalised patients at risk for pressure injury and then calibrate a machine learning model to predict future pressure injury risk. Optimisation methods combined with multilevel logistic regression were used to develop a predictive algorithm of patient-specific shifts in risk over time. Machine learning methods were tested, including random forests, to identify predictive features for the algorithm. We reported the results of the regression approach as well as the area under the receiver operating characteristics (ROC) curve for predictive models.
Hospitalised inpatients.
EHRs of 35 001 hospitalisations over 5 years across 2 academic hospitals.
Longitudinal shifts in pressure injury risk.
The predictive algorithm with features generated by machine learning achieved significantly improved prediction of pressure injury risk (p
These data could help hospitals conserve resources within a critical period of patient vulnerability of hospital-acquired pressure injury which is not reimbursed by US Medicare; thus, conserving between 30 000 and 90 000 labour-hours per year in an average 500-bed hospital. Hospitals can use this predictive algorithm to initiate a quality improvement programme for pressure injury prevention and further customise the algorithm to patient-specific variation by facility.
Pressure injury prevention is complex, and rates continue to rise. Checklists reduce human error, improve adherence and standardization with complex processes, focus attention on evidence-based practices derived from clinical practice guidelines and are arranged in a systematic manner to manage the entirety of a patient's risk for preventable outcomes. The original Standardized Pressure Injury Prevention Protocol was created to provide a checklist of pressure injury prevention measures but needed revision and validation.
This article describes the revision and content validity testing of the Standardized Pressure Injury Prevention Protocol Checklist 2.0 that took place in 2022.
Using the International 2019 Clinical Practice Guideline as a foundation, items were identified/revised, and expert review of the items was obtained. The Standardized Pressure Injury Prevention Protocol 2.0 underwent three rounds of revision by experts from the National Pressure Injury Advisory Panel. A panel of eight national experts completed the content validity survey. Individual item content validity index and total scale content validity index were used to summarize the content validity survey scores.
The individual item content validity index scores ranged from 0.5 to 1.0. One item (using a mirror to look at heels) was rated as 0.5, three items were 0.75, 20 items were 0.875 and 23 items were 1.0. The item scoring 0.5 was deleted. Those items scoring 0.75 were revised using the content experts' recommendations. The total scale content validity index was 0.93.
The Standardized Pressure Injury Prevention Protocol 2.0 provides a standardized checklist of evidence-based items that operationalize a rigorous clinical practice guideline for the prevention of pressure injuries. Early intervention using a standardized approach and evidence-based checklist that can be integrated into the workflow of the direct-care nurse and provider provides the best opportunity for successful and sustainable pressure injury prevention.
Pressure injury (PrI) prevention guidelines recommend 2-h repositioning intervals in healthcare settings, requiring significant nursing time investment. We analysed the cost-effectiveness of PrI prevention protocols with 2-, 3- and 4-h repositioning intervals in US nursing homes according to ‘Turn Everyone and Move for Ulcer Prevention’ (TEAM-UP) randomized controlled trial findings. Markov modelling compared 2-, 3- and 4-h repositioning intervals, controlling for other practice guidelines, to prevent PrIs in nursing home residents from a US health sector perspective over one year using TEAM-UP trial data for model structure, sampling and parameterization. Costs, captured in 2020 US dollars, and quality-adjusted life years (QALYs) were used to derive an incremental cost-effectiveness ratio and net monetary benefit (NMB) at $50 000/QALY-$150 000/QALY cost-effectiveness thresholds. Sensitivity analyses tested model uncertainty. Repositioning intervals between 3 and 4 h were cost-effective based on reduced costs at slightly lower QALYs than 2 h at a $50 000/QALY threshold, and the NMB of 4-h repositioning was also more efficient than at 3 h ($9610). Repositioning labour cost and prevention routines were among the most sensitive parameters. Sensitivity analyses demonstrated that 3- and 4-h intervals were cost-effective in over 65% of simulations at any cost-effectiveness threshold. Repositioning intervals of 3 to 4 h have potential to reduce nursing time costs without significant decrements in clinical benefits to nursing home residents. Clinical guidelines for PrI prevention should be updated to reflect TEAM-UP clinical and economic findings. Facilities can use cost-savings recuperated from nursing time to deploy to other patient safety priorities without seriously jeopardizing PrI safety.
FreshRSS 